ai-safety-foundation / sparse_autoencoderLinks
Sparse Autoencoder for Mechanistic Interpretability
☆276Updated last year
Alternatives and similar repositories for sparse_autoencoder
Users that are interested in sparse_autoencoder are comparing it to the libraries listed below
Sorting:
- Using sparse coding to find distributed representations used by neural networks.☆280Updated last year
- ☆355Updated 2 months ago
- ☆248Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆224Updated 10 months ago
- ☆131Updated last week
- ☆130Updated 2 years ago
- Sparsify transformers with SAEs and transcoders☆644Updated last week
- Mechanistic Interpretability Visualizations using React☆296Updated 10 months ago
- ☆181Updated 11 months ago
- ☆191Updated 2 weeks ago
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆685Updated this week
- Training Sparse Autoencoders on Language Models☆1,001Updated last week
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆219Updated last week
- Steering vectors for transformer language models in Pytorch / Huggingface☆126Updated 8 months ago
- ☆55Updated 11 months ago
- Steering Llama 2 with Contrastive Activation Addition☆191Updated last year
- ☆532Updated last year
- ☆127Updated last year
- This repository collects all relevant resources about interpretability in LLMs☆375Updated 11 months ago
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆292Updated 4 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆59Updated last year
- ☆206Updated 11 months ago
- Tools for understanding how transformer predictions are built layer-by-layer☆535Updated 2 months ago
- An Open Source Implementation of Anthropic's Paper: "Towards Monosemanticity: Decomposing Language Models with Dictionary Learning"☆49Updated last year
- ☆236Updated last year
- ☆74Updated 2 weeks ago
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆821Updated 2 weeks ago
- Sparse Autoencoder Training Library☆55Updated 5 months ago
- ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).☆315Updated 3 months ago
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆158Updated this week